gpt4free icon indicating copy to clipboard operation
gpt4free copied to clipboard

Confused with model response

Open ryukaizen opened this issue 1 year ago • 5 comments

Not really related to gpt4free but I still have some doubts that it might be related to gpt4free, correct me on that please

When asked "are you a llama model" to llama-3.1-405b model

The response consists

LLaMA is a specific language model developed by Meta, while I am a different model created by OpenAI

Client code:

from g4f.client import Client

client = Client()
response = client.chat.completions.create(
    model="llama-3.1-405b",
    messages=[{"role": "user", "content": "are you llama model"}],
    # Add any other necessary parameters
)
print(response.choices[0].message.content)

Full output:

Response to User's Query

No, I am not a LLaMA model. I am an AI language model designed to assist users with various inquiries and tasks.

Key Points

  • I provide information and support in a conversational manner.
  • My capabilities include answering questions, providing explanations, and assisting with various topics.
  • LLaMA is a specific language model developed by Meta, while I am a different model created by OpenAI.

If you have any specific questions or need assistance, feel free to ask!

I just wanted to know if the response is supposed to be as shown in the output(?). Is it the model's fault or it is related to gpt4free (or client code)?

Thanks in advance.

ryukaizen avatar Nov 01 '24 04:11 ryukaizen

from https://github.com/hqnicolas/continue4free probably llama server is down and switched to other server.... image

hqnicolas avatar Nov 01 '24 13:11 hqnicolas

@hqnicolas so it switched to gpt, is it expected behaviour?

In that case, is there any way I will get to know that the service or provider is down and will not just switch to different model.

ryukaizen avatar Nov 02 '24 16:11 ryukaizen

@ryukaizen

In that case, is there any way I will get to know that the service or provider is down and will not just switch to different model.

Service providers are registered in priority sequence within gpt4free not only can your provider change models without notifying gpt4free but gpt4free can also switch to another provider who may also have changed models. this creates a tree of possibilities that I don't have the capacity to deal with, sorry

hqnicolas avatar Nov 06 '24 13:11 hqnicolas

@hqnicolas ah I see, thanks for clarification

ryukaizen avatar Nov 07 '24 02:11 ryukaizen

Bumping this issue because it has been open for 7 days with no activity. Closing automatically in 7 days unless it becomes active again.

github-actions[bot] avatar Nov 15 '24 00:11 github-actions[bot]